This paper describes the string-to-tree systems built at the University of Edinburgh for the WMT 2014 shared translation task. We developed systems for English-German, Czech-English, FrenchEnglish, German-English, Hindi-English, and Russian-English. This year we improved our English-German system through target-side compound splitting, morphosyntactic constraints, and refinements to parse tree ...

This paper presents a new Slovenian spoken language resource built from TEDx Talks. The speech database contains 242 talks in total duration of 54 hours. The annotation and transcription of acquired spoken material was generated automatically, applying acoustic segmentation and automatic speech recognition. The development and evaluation subset was also manually transcribed using the guidelines...

With a strong motivational background in search engine optimization the amount of structured data on the web is growing rapidly. The main search engine providers are promising great increase in visibility through annotation of the web page’s content with the vocabulary of schema.org and thus providing it as structured data. But besides the usage by search engines the data can be used in various...

This paper presents how the TAAABLE project addresses the textual case-based reasoning challenge of the CCC, thanks to a combination of principles, methods, and technologies of various fields of knowledge-based system technologies, namely CBR, ontology engineering (manual and semi-automatic), data and text-mining using textual resources of the Web, text annotation (used as an indexing technique...

Assigning nomenclature codes to biomedical data is an arduous, expensive and error-prone task. Data records are coded to to provide a common representation of contained concepts, allowing facile retrieval of records via a standard terminology. In the medical field, cancer registrars, nurses, pathologists, and private clinicians all understand the importance of annotating medical records with vo...

SUMMARY The Gene Ontology (GO) is a controlled biological vocabulary that provides three structured networks of terms to describe biological processes, cellular components and molecular functions. Many databases of gene products are annotated using the GO vocabularies. We found that some GO-updating operations are not easily traceable by the current biological databases and GO browsers. Consequ...

This paper describes an innovative component of an e-learning platform targeted at second language training of medical professionals. This component provides interactive video learning material in three European languages: English, German and Spanish. The implemented prototype integrates storytelling technology with NLP and dynamic web engineering. Starting by the automatic annotation of releva...

The widespread development and adoption of ontologies to capture semantic domain knowledge and the growth of annotation graph datasets has created many opportunities for large scale Linked Data analytics. Ontologies are developed by domain experts to capture knowledge specific to some domain. The biomedical community has taken the lead in these activities. Every model organism database has gene...

What constitutes a scene? Defining a meaningful vocabulary for scene discovery is a challenging problem that has important consequences for object recognition. We consider scenes to depict correlated objects and present visual similarity. We introduce a max-margin factorization model that finds a low dimensional subspace with high discriminative power for correlated annotations. We postulate th...

This paper reports on the problems occurring in the process of building LVCSR (Large Vocabulary Continuous Speech Recognition) corpora based on the internal evaluation of the Polish database JURISDIC. The initial assumptions are discussed together with technical matters concerning the database realization and annotation results. Providing rich database statistics was considered crucial especial...